R Notebook

Calling relevant libraries

#READING THE DATA-SET

names(candy_data_all_years)

[1] "year"                    "age"                     "trick_or_treat_yourself" "candy_name"             
[5] "emotion"                 "gender"                  "country"                

Analysis questions

1> What is the total number of candy ratings given across the three years. (number of candy ratings, not number of raters. Don’t count missing values)

candy_data_all_years %>%
  filter(!is.na(emotion)) %>%
   summarise(total_no_of_candy_ratings = n())

2> What was the average age of people who are going out trick or treating and the average age of people 3. not going trick or treating?

candy_data_all_years %>%
  group_by(trick_or_treat_yourself) %>%
  summarise( average_age = mean(age,na.rm = TRUE))

NA

3> For each of joy, despair and meh, which candy bar revived the most of these ratings?

candy_data_all_years %>%
  filter(!is.na(emotion))%>%
  group_by(emotion, candy_name) %>%
  summarise( count = n()) %>%
  filter(count == max(count))

4> How many people rated Starburst as despair?

candy_data_all_years %>%
  filter(candy_name == "starburst", emotion == "DESPAIR") %>%
  summarise (total_starburst_despair = n())

For the next three questions, count despair as -1, joy as +1 and meh as 0.

5> What was the most popular candy bar by this rating system for each gender in the dataset?

6> What was the most popular candy bar in each year?

7> What was the most popular candy bar by this rating for people in US, Canada, UK and all other countries?